Benjamin Ellenberger

Node positions array/dict for post processing

4

I really like the visuals of the nxviz graphs over some of the networkx ones. However, in networkx I can easily access the node positions to add some additional annotations...

Make it compatible with the MuJoCo environments

3

First off, it needs to be compatible with agents trained on MuJoCo trained envs. Any contribution welcome of such agents! Just post here if you have a set of well...

Can parlMice continue imputation if insufficient convergence is detected?

3

Hi! I am trying to setup parlMice in the following way: ``` mdf

Why is the node_feature matrix + 1 larger than the largest index of nodes?

2

In the preprocess code you currently only use a zero matrix, so it does not matter in your experiments. https://github.com/twitter-research/tgn/blob/2aa295a1f182137a6ad56328b43cb3d8223cae77/utils/preprocess_data.py#L74 But why is the feature matrix one row larger than...

Migration to python3 and increase chance to make it run on your own machine

36

Migrate to python3 and pure keras, clean up and beautify the code, structure input and output data and added a requirement.txt and some nice READMEs. I hope this serves some...

How come the compiled version has more features than the source code?

2

I could at least spot that the compiled version has the instrument buttons. Also, would you mind releasing the model?

On segmentation faults happening in the line.cpp Update method

4

With one of my network graphs, I had several segmentation faults occurring, which I could locate within the update method of LINE. The problem is that if the embeddings get...

How to import data from views?

2

We are currently evaluating neo4j to export our RDBMS and then export the data into RDF through the RDF extension. Using the desktop ETL tools I can easily import tables,...

This updates all librosa and torch calls such that training on google speech commands works. What works so far: - google speech commands training What does not work so far:...

The generator does not work with non-square output sizes

3

I tried to print pydenticons for my numpy matrices, which works quite well for square input, but gets a problem with non-square identicons. ``` data = np.array2string(np_array) # Instantiate a...